content - Story 22779 | Emotion Vectors in Gemma4-31B

The courtroom was stuffy. Sarah, her face pale, listened as the will was read. Her brother, David, was now the owner of the family's successful law firm, his ambitions finally realized. Sarah got their mother’s recipe books.

She went home, and started making the recipes. Her kitchen became warm. She found a strange satisfaction from cooking each dish. She smiled, smelling the food. She thought of her mother, and the love she had felt for her family.

Emotion: content

Cluster: Calm / Serenity

PC1 (Valence): 2.98 Positive

PC2 (Disposition): -2.19

Role in Research

This story is one of 1,000 stories generated for the emotion content. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 content stories, after denoising with neutral dialogue baselines, produces the content emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the content vector is projected through the unembedding matrix.

Promoted:

`la`	0.446
`affectionately`	0.435
`😊`	0.392
`😊`	0.386
`thoughtful`	0.386

Suppressed:

`S`	-0.682
`L`	-0.537
`C`	-0.485
`😣`	-0.362
`est`	-0.350